Speech enhancement is fundamental for various real time speech applications and it is a challenging task in the case of a single channel because practically only one data channel is available. We have proposed a supervised single channel speech enhancement algorithm in this paper based on a deep neural network (DNN) and less aggressive Wiener filtering as additional DNN layer. During the training stage the network learns and predicts the magnitude spectrums of the clean and noise signals from input noisy speech acoustic features. Relative spectral transform-perceptual linear prediction (RASTA-PLP) is used in the proposed method to extract the acoustic features at the frame level. Autoregressive moving average (ARMA) filter is applied to smooth the temporal curves of extracted features. The trained network predicts the coefficients to construct a ratio mask based on mean square error (MSE) objective cost function. The less aggressive Wiener filter is placed as an additional layer on the top of a DNN to produce an enhanced magnitude spectrum. Finally, the noisy speech phase is used to reconstruct the enhanced speech. The experimental results demonstrate that the proposed DNN framework with less aggressive Wiener filtering outperforms the competing speech enhancement methods in terms of the speech quality and intelligibility.
Potato (Solanum tuberosum L.), an important food crop in the world, is susceptible to many fungal pathogens including Alternaria solani and Fusarium oxysporum causing Fusarium wilt and early blight diseases. Mycoparasitic fungi like Trichoderma encode chitinases, cell wall degrading enzymes, with high antifungal activity against a wide range of phytopathogenic fungi. In this study, a binary vector harboring endochitinase gene of ~1,000 bp was constructed and used to transform potato nodes through Agrobacterium-mediated transformation. Out of several primary transformants, two transgenic potato lines were verified for transgene insertion and integration by Southern blot. In a pot experiment for Fusarium resistance, the transgenic potato lines didn’t show any symptoms of disease, instead they remained healthy post infection. The transgenic potato lines exhibited 1.5 fold higher mRNA expression of endochitinase at 7 days as compared to 0 day post fungus inoculation. It was evident that the mRNA expression decreased over days of inoculation but was still higher than at 0 day and remained stable upto 30 days post inoculation. Similarly, for A. solani infection assay, the mRNA expression of the endochitinase gene was 3 fold higher 7 days post inoculation compared to expression at 0 day. Although the expression decreased by1.2 fold during subsequent days post infection, it remained stable for 30 days, suggesting that protection in transgenic potato plants against fungal pathogens was achieved through an increase in endochitinase transcript.